GL

zai org GLM 4.6

GLMGGUF by bartowskiUpdated 2025-10-02
Download on Hugging Face
Parameters357B
Context198K
Layers93
Architectureglm4moe
Smallest quant0.7 GB
Quick answer

zai org GLM 4.6 needs about 221.3 GB of memory at Q4_K_M (a 217.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.7 GB to 379.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.5 GB.

GLM‑4.6, a 357‑billion‑parameter mixture‑of‑experts model with a 200K‑token context window

GLM‑4.6 expands the context window to 200K tokens and improves coding, reasoning, and agent performance. It supports tool use during inference and integrates well with agent frameworks. The model is released under the MIT license.

Good at

  • Long‑context reasoning
  • Advanced coding performance
  • Tool‑enabled agent tasks

Limits

  • Requires large VRAM for full precision
  • No vision support
  • Mixture‑of‑experts architecture limits single‑GPU inference

Best for

  • Complex agentic workflows
  • Large‑scale code generation
  • Long‑form document analysis

Who it’s for. Developers and researchers needing a high‑capacity language model for extended context and agentic tasks. The model is suitable for applications that can accommodate its memory footprint and mixture‑of‑experts design.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.7 GB 4.3 GB
Fits Get file →
IQ1_S76.3 GB (2 parts) 79.9 GB
Too big Get file →
IQ1_M79.6 GB (2 parts) 83.2 GB
Too big Get file →
IQ2_XXS88.3 GB (3 parts) 91.9 GB
Too big Get file →
IQ2_XS101.0 GB (3 parts) 104.7 GB
Too big Get file →
IQ2_S101.9 GB (3 parts) 105.5 GB
Too big Get file →
IQ2_M115.3 GB (3 parts) 118.9 GB
Too big Get file →
Q2_K127.2 GB (4 parts) 130.9 GB
Too big Get file →
Q2_K_L128.0 GB (4 parts) 131.6 GB
Too big Get file →
IQ3_XXS142.7 GB (4 parts) 146.3 GB
Too big Get file →
IQ3_XS148.2 GB (4 parts) 151.8 GB
Too big Get file →
Q3_K_S156.7 GB (4 parts) 160.3 GB
Too big Get file →
IQ3_M164.3 GB (5 parts) 167.9 GB
Too big Get file →
Q3_K_M164.3 GB (5 parts) 167.9 GB
Too big Get file →
Q3_K_L169.9 GB (5 parts) 173.5 GB
Too big Get file →
Q3_K_XL170.6 GB (5 parts) 174.2 GB
Too big Get file →
IQ4_XS192.0 GB (5 parts) 195.6 GB
Too big Get file →
IQ4_NL202.9 GB (6 parts) 206.5 GB
Too big Get file →
Q4_0205.6 GB (6 parts) 209.2 GB
Too big Get file →
Q4_K_S209.9 GB (6 parts) 213.5 GB
Too big Get file →
Q4_K_M217.7 GB (6 parts) 221.3 GB
Too big Get file →
Q4_1224.2 GB (6 parts) 227.8 GB
Too big Get file →
Q5_K_S246.4 GB (7 parts) 250.0 GB
Too big Get file →
Q5_K_M254.2 GB (7 parts) 257.8 GB
Too big Get file →
Q6_K293.6 GB (8 parts) 297.2 GB
Too big Get file →
Q8_0379.3 GB (10 parts) 382.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (≈209 GB file, 213.5 GB memory at 8 k context). For 16 GB VRAM, Q5_K_S or Q5_K_M (≈246 GB file, 250 GB memory). For 24 GB VRAM, Q6_K (≈293 GB file, 297.2 GB memory).

What GPU do you need for zai org GLM 4.6?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.7 GB file, about 4.3 GB in use).

Which zai org GLM 4.6 quant should you choose?

Q4_K_M is the usual starting point for zai org GLM 4.6: it balances file size and quality well. Here it is a 217.7 GB file.

The Q8_0 file is 379.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters357B (approximate, mixture of experts)
Layers93
Trained context202,752 tokens
KV cache (fp16)372 KB per token

Source

Quantized bybartowski
FamilyGLM
Base modelzai-org/GLM-4.6
Licensemit
Downloads (HF)2,097
Last updated2025-10-02

Frequently asked questions about zai org GLM 4.6

How much VRAM does zai org GLM 4.6 need?

About 221.3 GB at Q4_K_M with an 8K context window. That is the 217.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run zai org GLM 4.6 on an 8 GB GPU?

Yes, with the smaller files: the 0.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of zai org GLM 4.6 GGUF?

It depends on the quant: file is 0.7 GB, IQ1_S is 76.3 GB, IQ1_M is 79.6 GB, IQ2_XXS is 88.3 GB, IQ2_XS is 101.0 GB, IQ2_S is 101.9 GB and 20 more.

What context length does zai org GLM 4.6 support?

The GGUF header lists a trained context length of 202,752 tokens (198K). The KV cache grows with the context you use: about 3.1 GB at 8K and 12.5 GB at 32K.

Where can I download zai org GLM 4.6 GGUF?

The files are on Hugging Face in the bartowski/zai-org_GLM-4.6-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does zai org GLM 4.6 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run GLM‑4.6 on 8 GB VRAM?

Only the lowest‑precision quants such as Q4_0 or Q4_K_S can fit, but they still require over 200 GB of memory at 8 k context, so 8 GB VRAM is insufficient.

Does GLM‑4.6 support vision?

No, the model has no vision capabilities.

What license does GLM‑4.6 use?

The model is released under the MIT license.

Other GGUFs of GLM-4.6

Similar models

Browse all →

More from bartowski

All by bartowski →

More GLM models

All GLM →

Other large models

All large models →